An interactive Ascend-NPU process viewer

A general-purpose real-time streaming media and deep learning inference acceleration framework, supporting H264, H265, AAC, MP4, FLV, RTSP, RTMP, and YOLO.实时流媒体及深度学习推理加速通用处理框架，支持H264、H265、AAC、MP4、FLV、RTSP、RTMP、YOLO。

TileXR (eXtreme Rendezvous for Asynchronous Tile Communication) is a data-centric asynchronous communication runtime for Huawei Ascend NPUs.

Ascend NPU fork of nanochat for LLM training with torch_npu/HCCL (experimental)

Run nanochat training efficiently on Huawei Ascend NPUs with minimal code changes, supporting tokenizer, pretraining, and evaluation workflows.

A repository to store neural network test code.

Cholesky decomposition reference implementation on Ascend NPU

Minimal runnable Ascend C (CANN) operator examples on cannsim card-free (no-NPU) CAModel simulation

Automated GLM interaction detection via CANN, NID scores, and SHAP interaction values for insurance pricing.

Run and validate Huawei Ascend CANN/AscendCL operator code on commodity GPUs — a backend-portable reimplementation of acl/aclnn/HCCL.

Predicting California house prices with MindSpore

C++ YOLO26 deployment demos for Huawei Atlas using CANN/AscendCL, with FP16 AIPP detection and tracking examples.

Deploy GLM-4.6V-Flash (9B dense VLM) on Huawei Ascend 910B NPU with vLLM - multimodal, OpenAI API, single/dual-card serving, reproducible benchmarks.

Linear classification of CIFAR-10 dataset with MindSpore

Read-only mirror of https://gitcode.com/donaldsebleung/my-ascend-notebook-images

Read-only mirror of https://gitcode.com/donaldsebleung/my-ascend-gitops

Read-only mirror of https://gitcode.com/donaldsebleung/my-ascend-notebooks